© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39282
    Prev
    Next
    INDEX
    Explanations

    select the forum that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    佬
    -0.07
    ä½ľçĶ»
    -0.07
    ắp
    -0.07
    .Configuration
    -0.07
    refour
    -0.07
    idea
    -0.06
    æĭİçĿĢ
    -0.06
    berra
    -0.06
    ICO
    -0.06
    afort
    -0.06
    POSITIVE LOGITS
    uth
    0.07
    ç¼Ń
    0.07
    çªĸ
    0.07
    alp
    0.06
    Licensed
    0.06
    åĽĽå°Ħ
    0.06
    æ½
    0.06
    ../../../../
    0.06
    æµ·å¸Ĥ
    0.06
    bien
    0.06
    Activations Density 0.008%

    No Known Activations